SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation

Yuqi Fan, Zhiyong Cui, Zhenning Li, Yilong Ren, Haiyang Yu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15719-15735, 2025.

Abstract

Reliable planning is crucial for achieving autonomous driving. Rule-based planners are efficient but lack generalization, while learning-based planners excel in generalization yet have limitations in real-time performance and interpretability. In long-tail scenarios, these challenges make planning particularly difficult. To leverage the strengths of both rule-based and learning-based planners, we proposed the Scenario-Aware Hybrid Planner (SAH-Drive) for closed-loop vehicle trajectory planning. Inspired by human driving behavior, SAH-Drive combines a lightweight rule-based planner and a comprehensive learning-based planner, utilizing a dual-timescale decision neuron to determine the final trajectory. To enhance the computational efficiency and robustness of the hybrid planner, we also employed a diffusion proposal number regulator and a trajectory fusion module. The experimental results show that the proposed method significantly improves the generalization capability of the planning system, achieving state-of-the-art performance in interPlan, while maintaining computational efficiency without incurring substantial additional runtime.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-fan25c, title = {{SAH}-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation}, author = {Fan, Yuqi and Cui, Zhiyong and Li, Zhenning and Ren, Yilong and Yu, Haiyang}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {15719--15735}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/fan25c/fan25c.pdf}, url = {https://proceedings.mlr.press/v267/fan25c.html}, abstract = {Reliable planning is crucial for achieving autonomous driving. Rule-based planners are efficient but lack generalization, while learning-based planners excel in generalization yet have limitations in real-time performance and interpretability. In long-tail scenarios, these challenges make planning particularly difficult. To leverage the strengths of both rule-based and learning-based planners, we proposed the Scenario-Aware Hybrid Planner (SAH-Drive) for closed-loop vehicle trajectory planning. Inspired by human driving behavior, SAH-Drive combines a lightweight rule-based planner and a comprehensive learning-based planner, utilizing a dual-timescale decision neuron to determine the final trajectory. To enhance the computational efficiency and robustness of the hybrid planner, we also employed a diffusion proposal number regulator and a trajectory fusion module. The experimental results show that the proposed method significantly improves the generalization capability of the planning system, achieving state-of-the-art performance in interPlan, while maintaining computational efficiency without incurring substantial additional runtime.} }
Endnote
%0 Conference Paper %T SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation %A Yuqi Fan %A Zhiyong Cui %A Zhenning Li %A Yilong Ren %A Haiyang Yu %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-fan25c %I PMLR %P 15719--15735 %U https://proceedings.mlr.press/v267/fan25c.html %V 267 %X Reliable planning is crucial for achieving autonomous driving. Rule-based planners are efficient but lack generalization, while learning-based planners excel in generalization yet have limitations in real-time performance and interpretability. In long-tail scenarios, these challenges make planning particularly difficult. To leverage the strengths of both rule-based and learning-based planners, we proposed the Scenario-Aware Hybrid Planner (SAH-Drive) for closed-loop vehicle trajectory planning. Inspired by human driving behavior, SAH-Drive combines a lightweight rule-based planner and a comprehensive learning-based planner, utilizing a dual-timescale decision neuron to determine the final trajectory. To enhance the computational efficiency and robustness of the hybrid planner, we also employed a diffusion proposal number regulator and a trajectory fusion module. The experimental results show that the proposed method significantly improves the generalization capability of the planning system, achieving state-of-the-art performance in interPlan, while maintaining computational efficiency without incurring substantial additional runtime.
APA
Fan, Y., Cui, Z., Li, Z., Ren, Y. & Yu, H.. (2025). SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:15719-15735 Available from https://proceedings.mlr.press/v267/fan25c.html.

Related Material